CN115994627B - Residential building flexible load day-ahead optimal scheduling method, device, equipment and medium - Google Patents
Residential building flexible load day-ahead optimal scheduling method, device, equipment and medium Download PDFInfo
- Publication number
- CN115994627B CN115994627B CN202310280030.1A CN202310280030A CN115994627B CN 115994627 B CN115994627 B CN 115994627B CN 202310280030 A CN202310280030 A CN 202310280030A CN 115994627 B CN115994627 B CN 115994627B
- Authority
- CN
- China
- Prior art keywords
- model
- load
- day
- optimal scheduling
- ahead
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000005457 optimization Methods 0.000 claims abstract description 41
- 230000005611 electricity Effects 0.000 claims abstract description 40
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims abstract description 26
- 230000009194 climbing Effects 0.000 claims abstract description 15
- 229910002092 carbon dioxide Inorganic materials 0.000 claims abstract description 13
- 239000001569 carbon dioxide Substances 0.000 claims abstract description 13
- 238000010276 construction Methods 0.000 claims abstract description 9
- 230000006399 behavior Effects 0.000 claims description 117
- 238000009826 distribution Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000003068 static effect Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 10
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000011161 development Methods 0.000 claims description 4
- 230000008685 targeting Effects 0.000 claims 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 27
- 230000008569 process Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005406 washing Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a residential building flexible load day-ahead optimal scheduling method, device, equipment and medium, relates to the technical field of housing construction, and comprises the following steps: constructing a day-ahead optimal scheduling model which aims at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission; taking a flexible load characteristic model, a random human behavior model and a power prediction model as constraint conditions of a day-ahead optimization scheduling model; and solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain the day-ahead optimal scheduling scheme of the flexible load of the residential building. The flexible load characteristic model, the random human behavior model and the power prediction model are used as constraint conditions, so that the daily optimization scheduling model is solved, the influence of the random human behavior of a user on flexible load optimization scheduling of the residential building is comprehensively considered, and the daily optimization scheduling scheme formed by solved parameters can be better executed in actual engineering.
Description
Technical Field
The invention relates to the field of housing construction, in particular to a method, a device, equipment and a medium for day-ahead optimal scheduling of flexible loads of a housing construction.
Background
Residential building load flexibility has received considerable attention in recent years as an effective way to address the imbalance of supply and demand in high-ratio renewable energy power systems. By adjusting the set temperature of the isothermal load control of the residential building air conditioner and the electric water heater, the working time of the transferable load such as the washing machine, the dryer, the dish washer and the like is transferred, and auxiliary service can be provided for the power grid, so that the influence of the intermittence of photovoltaic power generation, wind power generation and the like on the power grid is reduced. However, how to efficiently schedule flexible loads such as temperature controlled loads and transferable loads presents a significant challenge. Since the optimal scheduling of the flexible load is influenced by the user's use behavior (hereinafter referred to as "human behavior") of the home appliance, the user's human behavior is closely related to the user's life style, preference, occupation, etc., and there is a great difference between different households. The high degree of uncertainty and complexity in user human behavior makes optimal scheduling of residential building flexible loads more difficult. The current method for optimizing and dispatching the flexible load of the residential building can be summarized as follows: firstly, a flexible load characteristic model is established, then an optimization model is established by taking the minimum daily operation cost as an optimization target, and a linear programming or artificial intelligent algorithm is adopted to solve the flexible load daily optimization scheduling scheme.
In summary, how to fully consider the behavior characteristics of the user and ensure the effectiveness of the optimal scheduling scheme before the day of the obtained flexible load, so that the scheduling scheme can be effectively executed in practical engineering application is a technical problem to be solved in the field.
Disclosure of Invention
In view of the above, the invention aims to provide a residential building flexible load day-ahead optimal scheduling method, device, equipment and medium, which can fully consider the behavior characteristics of users and ensure the effectiveness of an obtained flexible load day-ahead optimal scheduling scheme, so that the scheduling scheme can be effectively executed in practical engineering application. The specific scheme is as follows:
in a first aspect, the application discloses a residential building flexible load day-ahead optimal scheduling method, which comprises the following steps:
constructing a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission;
taking a flexible load characteristic model, a random human behavior model and a power prediction model as constraint conditions of the day-ahead optimization scheduling model;
and solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain a day-ahead optimal scheduling scheme of the flexible load of the residential building.
Optionally, before the constraint condition of the day-ahead optimization scheduling model is taken as the flexible load characteristic model, the random pedestrian behavior model and the power prediction model, the method further includes:
and constructing a flexible load characteristic model comprising a temperature control load characteristic model and a transferable load characteristic model.
Optionally, before the constraint condition of the day-ahead optimization scheduling model is taken as the flexible load characteristic model, the random pedestrian behavior model and the power prediction model, the method further includes:
a random human behavior model for determining human behavior of the user is established using a preset machine learning algorithm.
Optionally, the establishing a random human behavior model for determining human behavior of the user by using a preset machine learning algorithm includes:
and determining a pedestrian behavior characteristic parameter describing the behavior of the user aiming at the flexible load person and probability distribution of the pedestrian behavior characteristic parameter, and establishing a Monte Carlo random pedestrian behavior model based on a Markov chain.
Optionally, the determining a human behavior characteristic parameter describing the behavior of the user for the flexible load person and a probability distribution of the human behavior characteristic parameter, and establishing a monte carlo random human behavior model based on a markov chain, includes:
Determining a pedestrian behavior static characteristic parameter, a discrete type pedestrian behavior dynamic characteristic parameter and a continuous type pedestrian behavior dynamic characteristic parameter;
determining probability distribution of the discrete human behavior dynamic characteristic parameters in a frequency estimation mode;
visualizing the continuous type pedestrian behavior dynamic characteristic parameters, and determining probability distribution of the continuous type pedestrian behavior dynamic characteristic parameters by utilizing a parameter estimation mode;
a random human behavior model for determining the human behavior of the user is established by adopting a Markov chain Monte Carlo method based on Metropolis Hasting algorithm.
Optionally, before the constraint condition of the day-ahead optimization scheduling model is taken as the flexible load characteristic model, the random pedestrian behavior model and the power prediction model, the method further includes:
based on historical inflexible load power data of the inflexible load power, the current inflexible load power is predicted by a heuristic prediction method.
Optionally, the solving the day-ahead optimal scheduling model by using a linear programming method to obtain a day-ahead optimal scheduling scheme of the flexible load of the residential building includes:
writing the day-ahead optimal scheduling model, the flexible load characteristic model, the random human behavior model and the power prediction model into an integrated development environment through a programming language to generate a solving tool;
And calling a preset cvxpy library by using the solving tool to solve the day-ahead optimal scheduling model so as to obtain an optimal solution of flexible load optimal scheduling of the residential building.
In a second aspect, the present application discloses a residential building flexible load day-ahead optimal scheduling device, comprising:
the model construction module is used for constructing a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission;
the constraint condition determining module is used for taking the flexible load characteristic model, the random pedestrian behavior model and the power prediction model as constraint conditions of the day-ahead optimal scheduling model;
and the solving module is used for solving the day-ahead optimal scheduling model by adopting a linear programming method so as to obtain a flexible load day-ahead optimal scheduling scheme of the residential building.
In a third aspect, the present application discloses an electronic device comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the residential building load scheduling method disclosed previously.
In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein the computer program when executed by the processor implements the steps of the residential building flexible load day-ahead optimal scheduling method disclosed previously.
From this, the application discloses a residential building flexible load day-ahead optimization scheduling method, which comprises the following steps: constructing a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission; taking a flexible load characteristic model, a random human behavior model and a power prediction model as constraint conditions of the day-ahead optimization scheduling model; and solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain a flexible load day-ahead optimal scheduling scheme of the residential building. Therefore, the condition constraint is carried out on the established mixed integer linear programming day-ahead optimal scheduling model, the flexible load characteristic model, the random pedestrian behavior model and the power prediction model are used as constraint conditions, the day-ahead optimal scheduling model is further solved, the influence of random pedestrian behaviors of users in the flexible load optimal scheduling process of the residential building is comprehensively considered, and the optimal scheduling scheme composed of solved parameters can be executed in actual engineering.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a residential building flexible load day-ahead optimal scheduling method disclosed in the application;
FIG. 2 is a flow chart of a method for optimizing and dispatching flexible loads of a specific residential building in the future;
FIG. 3 is a flow chart of another specific residential building flexible load day-ahead optimal scheduling method disclosed in the present application;
FIG. 4 is a schematic structural diagram of a flexible load day-ahead optimal scheduling device for residential buildings disclosed in the application;
fig. 5 is a block diagram of an electronic device disclosed in the present application.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Residential building load flexibility has received considerable attention in recent years as an effective way to address the imbalance of supply and demand in high-ratio renewable energy power systems. By adjusting the set temperature of the isothermal load control of the residential building air conditioner and the electric water heater, the working time of the transferable load such as the washing machine, the dryer, the dish washer and the like is transferred, and auxiliary service can be provided for the power grid, so that the influence of the intermittence of photovoltaic power generation, wind power generation and the like on the power grid is reduced. However, how to efficiently schedule flexible loads such as temperature controlled loads and transferable loads presents a significant challenge. Since the optimal scheduling of the flexible load is influenced by the user's use behavior (hereinafter referred to as "human behavior") of the home appliance, the user's human behavior is closely related to the user's life style, preference, occupation, etc., and there is a great difference between different households. The high degree of uncertainty and complexity in user human behavior makes optimal scheduling of residential building flexible loads more difficult. The current method for optimizing and dispatching the flexible load of the residential building can be summarized as follows: firstly, a flexible load characteristic model is established, then an optimization model is established by taking the minimum daily operation cost as an optimization target, and a linear programming or artificial intelligent algorithm is adopted to solve the flexible load daily optimization scheduling scheme.
Therefore, the residential building flexible load day-ahead optimal scheduling scheme provided by the application can fully consider the behavior characteristics of the user, and the effectiveness of the obtained flexible load day-ahead optimal scheduling scheme is ensured, so that the scheduling scheme can be effectively executed in practical engineering application.
Referring to fig. 1, the embodiment of the invention discloses a residential building load scheduling method, which comprises the following steps:
step S11: and constructing a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission.
In this embodiment, the day-ahead optimal scheduling model mainly includes three parts: decision variables, objective functions and constraints. Wherein the decision variables include: the set temperature of the temperature controlled load and the transferable load start operating time. The objective function is that different stakeholders are involved in daily optimization scheduling of flexible load, and the interests concerned by each stakeholder are different, the user pays for electricity, the power grid pays for the influence of the user's electricity on the power grid, and the society pays for CO 2 And (5) discharging. Therefore, the average climbing rate of the electricity consumption curve of the user is minimized and the CO is minimized by the daily electricity cost 2 Emission minimization is an optimization objective, and three objective functions are converted into one objective function through a normalization weighting method, and the formula is as follows:
wherein, in the formula, the chemical formula,
，/>
，/>respectively representing the electricity cost of the objective function, the average climbing rate of the electricity curve of the user and CO 2 Exhaust (S)>
，/>
，/>
Respectively represent the electricity cost of the objective function and the electricity consumption of the userCurve average ramp rate and CO 2 Discharging the corresponding weight; />
，/>
Respectively representing the maximum value and the minimum value corresponding to the objective function.
Determining the electricity cost of an objective function, the average ramp rate of a user electricity curve and CO 2 The emissions are obtained by the following formula, in particular:
wherein,,
representing a price of electricity purchased from a grid; />
Representing power drawn from the grid; />
Is the time step; />
Representing the number of time steps; />
CO representing electric power 2 Equivalent emission factor of (c).
Step S12: and taking the flexible load characteristic model, the random human behavior model and the power prediction model as constraint conditions of the day-ahead optimization scheduling model.
The constraint conditions include: the energy balance constraint, the optimization space constraint of the decision variable and the operation constraint, wherein the energy balance constraint represents the energy flow balance of the whole system, namely the power taken from the power grid at a certain moment is equal to the sum of the power consumption of the flexible load and the power consumption of the non-flexible load at the moment, and the energy balance constraint can be represented by the following formula:
Wherein,,
，/>
and->
The flexible load characteristic model is calculated; />
Calculated from a power prediction model of the inflexible load.
The optimization space constraint of the decision variable indicates that the decision variable can only be optimized within a certain range, and can be expressed by the following formula:
wherein,,
、/>
respectively representing the minimum value and the maximum value of the air conditioner set temperature used by the user; />
、/>
Respectively representing the minimum value and the maximum value of the set temperature of the water storage type electric water heater used by a user; />
、/>
Representing the minimum and maximum values, respectively, of the transferable load start-up time that the user is accustomed to. The parameters are static characteristic parameters of the user behavior and are obtained through calculation through the established random human behavior model.
The operation constraint represents the constraint of the flexible load in the operation process, the constraint of the boundary conditions such as the use frequency, the opening time, the operation duration and the like is included for the temperature control load, and the constraint of the boundary conditions such as the use frequency, the operation mode and the like is included for the transferable load. The parameters are dynamic characteristic parameters of the user behavior and are obtained through calculation through the established random human behavior model.
Step S13: and solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain a flexible load day-ahead optimal scheduling scheme of the residential building.
In this embodiment, since the objective function, constraint condition, and the like of the day-ahead optimization scheduling model constructed are all linear, the optimization model is solved by adopting a linear programming method to obtain an optimal solution, so as to form an optimal scheduling scheme.
It can be seen that the present application discloses a residential building load scheduling method comprising: constructing a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission; taking a flexible load characteristic model, a random human behavior model and a power prediction model as constraint conditions of the day-ahead optimization scheduling model; and solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain an optimal solution of flexible load optimal scheduling of the residential building. Therefore, the condition constraint is carried out on the established mixed integer linear programming day-ahead optimal scheduling model, the flexible load characteristic model, the random pedestrian behavior model and the power prediction model are used as constraint conditions, the day-ahead optimal scheduling model is further solved, the influence of random pedestrian behaviors of users in the flexible load optimal scheduling process of the residential building is comprehensively considered, and the optimal scheduling scheme composed of solved parameters can be executed in actual engineering.
Referring to fig. 2, the embodiment of the invention discloses a specific residential building load scheduling method, and compared with the previous embodiment, the embodiment further describes and optimizes the technical scheme. Specific:
step S21: and constructing a flexible load characteristic model comprising a temperature control load characteristic model and a transferable load characteristic model.
In this embodiment, since the residential building load includes a flexible load and an inflexible load, the flexible load can be further divided into a temperature-controlled load and a transferable load. The temperature control load mainly comprises an air conditioner and a water storage type electric water heater, and for the household appliances, the electricity utilization curve of the household appliances can be changed by adjusting the set temperature of the household appliances; the transferable loads mainly comprise washing machines, dish washers and dryers, and for such household appliances, the electric loads thereof can be transferred by adjusting the running time thereof. The inflexible load mainly comprises a refrigerator, a smoke exhaust ventilator, a television, a computer and the like. It should be noted that the building load flexibility is that on the premise of not damaging the benefit of a user, the user changes the self electricity consumption curve of the building by reducing, transferring and improving the electricity consumption power of the flexible load, thereby matching intermittent renewable energy source power generation, improving the consumption of renewable energy source power and reducing the influence of the intermittent property and the fluctuation of the renewable energy source power on a power grid. Respectively constructing a temperature control load characteristic model and a transferable load characteristic model based on a data driving method, and then determining a flexible load characteristic model according to the temperature control load characteristic model and the transferable load characteristic model, wherein the temperature control load characteristic model specifically comprises: the split air conditioner characteristic model comprises two parts: a power model and a thermodynamic model. The power model describes the relation between the refrigerating capacity/heating capacity of the air conditioner and the power of the air conditioner, and can be expressed by the following formula:
Wherein,,
representing the running power of the air conditioner; />
Is a binary variable; />
And->
Two parameters which are the most important of the air conditioner power model, < ->
Indicating the power of the air conditioner in on state, +.>
The power of the air conditioner in the off state is represented, and the power can be calculated according to the actual operation data of the air conditioner. />
，/>
，/>
And->
The temperature of the indoor air, the set temperature of the air conditioner, the dead zone temperature of the air conditioner and the outdoor environment temperature are respectively; />
Indicating the cold or heat provided by the air conditioner; />
The energy conversion coefficient of the air conditioner is represented; />
Representing the rated energy conversion coefficient of the air conditioner; the thermodynamic model describes the dynamic heat exchange process of air in a room with a building envelope, an outdoor environment, an air conditioner, etc., and can be represented by the following formula:
wherein,,
，/>
，/>
and->
The model parameters are constant, and can be calculated by adopting a multiple linear regression method according to the actual operation data of the air conditioner. />
Indicating the heat gain from solar radiation.
The water-type electric water heater is similar to the air conditioner characteristic model, and the characteristic model of the water-storage type electric water heater also comprises a power model and a thermodynamic model. The power model may be represented by the following equation:
wherein,,
the power of the electric water heater in the on state is indicated, and the power can be calculated according to the actual operation data of the electric water heater. / >
Indicating the heat provided by the electric water heater; />
Is a binary variable; />
Indicating the heating efficiency of the electric water heater;
，/>
，/>
the temperature of hot water in the electric water heater, the set temperature of the electric water heater and the dead zone temperature of the electric water heater are respectively indicated. The thermodynamic model of an electric water heater can be represented by the following two formulas,
wherein the first formula represents a thermodynamic model of the electric water heater without hot water consumption and the second formula represents a thermodynamic model of the electric water heater with hot water consumption,
，/>
and->
The model parameters are constant, and can be calculated by adopting a multiple linear regression method according to the actual operation data of the electric water heater. />
Indicating the temperature of the surrounding environment of the electric water heater; />
Indicating the temperature of the cold water supplemented by the electric water heater; />
And->
Indicating the rated volume of the electric water heater and the amount of hot water consumed, respectively.
Wherein,,
power representing the w operating phase of the transferable load in the j operating mode, < >>
Representing transferable loadsDuration of the w operating phase in the j operating mode, +.>
Representing the duration of the entire operating cycle of the transferable load in the j operating mode.
Step S22: based on historical inflexible load power data of the inflexible load power, the current inflexible load power is predicted by a heuristic prediction method.
In this embodiment, when the day-ahead optimal scheduling of the flexible load is performed, it is necessary to predict the power consumption of the inflexible load at each time in advance. Because the power of the inflexible load generally has little change and is relatively stable, the power of the inflexible load is predicted by adopting a heuristic prediction method. Using the average power curve of the inflexible load for the past week as the predicted value of the electric power used before the day of the inflexible load, wherein
Wherein,,
predictive value representing the electric power used before the day of the inflexible load,/->
The historical inflexible load power on the day of the past is represented.
Step S23: and constructing a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission.
Step S24: and taking the flexible load characteristic model, the random human behavior model and the predicted value as constraint conditions of the daily optimization scheduling model.
Step S25: and solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain an optimal solution of flexible load optimal scheduling of the residential building.
The more detailed processing procedures in steps S23, S24, and S25 refer to the content of the foregoing disclosed embodiments, and are not described herein.
Therefore, the temperature control load characteristic model and the transferable load characteristic model are utilized to complete the determination of the flexible load characteristic condition, a heuristic prediction method and a historical inflexible load power are adopted to predict the predicted value of the current inflexible load power, so that the constraint condition of the constructed flexible load optimization scheduling model is formed, the finally solved optimal solution is more fit with actual production life, and the generated scheduling scheme can be effectively executed in actual engineering application.
Referring to fig. 3, the embodiment of the present invention discloses another specific residential building load scheduling method, and compared with the previous embodiment, the present embodiment further describes and optimizes the technical scheme. Specific:
step S31: a random human behavior model for determining human behavior of the user is established using a preset machine learning algorithm.
In this embodiment, constructing a random human behavior model specifically includes: and determining a human behavior characteristic parameter describing the behavior of the user aiming at the flexible load human, and probability distribution of the human behavior characteristic parameter, and establishing a random human behavior model for determining the human behavior of the user by establishing a Markov chain Monte Carlo method based on a Metropolis Hasting algorithm.
Two factors need to be considered when determining the characteristic parameters of the human behavior, firstly, the operation characteristics of the flexible load need to be considered, and the selected characteristic parameters need to be capable of completely describing the operation process of the flexible load, such as a plurality of times of use each day, a time of starting each time, a duration of each operation and the like. In addition, the problem of day-ahead optimal scheduling of flexible load is also required to be considered when the characteristic parameters are determined. In the optimal scheduling process, the set temperature of the temperature control load is adjusted and the working time of the transferable load is changed, so that the user is uncomfortable and inconvenient to heat, and in order to reduce the dissatisfaction of the user, the set temperature needs to be ensured to be within the set temperature range of the habit of the user when the set temperature of the temperature control load is adjusted, and the use time needs to be ensured to be within the use time range of the habit of the user when the working time of the transferable load is changed. Therefore, a characteristic parameter of "temperature setting preference" is proposed to describe the habit of the user's temperature setting, and a characteristic parameter of "flexible window" is proposed to describe the habit of the user's transferable load operating time. It is noted that such parameters are static characteristic parameters, since the temperature setting preferences and the flexible window are related to the habit of the user for using the household appliance, and generally do not change, depending on the user only. The proposed dynamic and static characteristic parameters are summarized as follows: dynamic characteristic parameters: for a temperature controlled load, comprising: frequency of use per day, opening time and operation duration; for transferable loads, comprising: frequency of use per day, mode of operation. Static characteristic parameters: for a temperature controlled load, comprising: a temperature setting preference; for transferable loads, comprising: a flexible window.
As for the dynamic characteristic parameters, since the dynamic characteristic parameters vary with time and each day, it is necessary to construct a random human behavior model so as to determine the dynamic characteristic parameters describing the user's daily human behavior. For static characteristic parameters, the parameters represent the behavior habits of users and are not changed generally, so that the values of the parameters can be statistically summarized from historical data based on the historical operation data by adopting a statistical analysis method. The modeling method of the random pedestrian model is mainly described below.
In this embodiment, when a random behavior model is established, a static behavior characteristic parameter, a discrete type behavior dynamic characteristic parameter and a continuous type behavior dynamic characteristic parameter are required to be determined; determining probability distribution of the discrete human behavior dynamic characteristic parameters in a frequency estimation mode; and visualizing the dynamic characteristic parameters of the continuous type pavement, and determining probability distribution of the dynamic characteristic parameters of the continuous type pavement by utilizing a parameter estimation mode.
Among the proposed dynamic characteristics parameters are discrete (frequency of use per day, mode of operation) and continuous (on-time, duration of operation) parameters. Based on statistical knowledge, the frequency is known to be an estimate of the probability, which is a steady value of the frequency. Thus, for discrete dynamic characteristic parameters, the probability distribution of the discrete dynamic characteristic parameters is estimated by using frequency based on actual operation data, and specifically the following formula can be expressed:
Wherein i represents a discrete dynamic characteristic parameter;
the probability when the discrete dynamic characteristic parameter i is x is represented; />
Representing the number contained in a sample with the value x of the discrete dynamic characteristic parameter i; />
Indicating the total number of samples monitored.
For continuous dynamic characteristic parameters, a parameter estimation method is adopted to determine probability distribution, specifically, the distribution of the dynamic characteristic parameters is visualized through a histogram method, the distribution characteristics of the dynamic characteristic parameters are analyzed, and then known distributions (namely, a parameter estimation method) such as Gaussian analysis, poisson distribution, lognormal distribution and the like are adopted to fit and determine probability distribution p (x) of the continuous dynamic characteristic parameters. The determining of the dynamic characteristic parameters of the continuous type person comprises the following steps: and determining the dynamic characteristic parameters of the continuous type pedestrian behavior based on a random pedestrian behavior model.
In this embodiment, a random human behavior model is established by adopting a markov chain monte carlo method based on Metropolis Hasting algorithm, so as to determine dynamic characteristic parameters of a user, and the specific steps are as follows:
initializing continuous dynamic characteristic parameter x 0 （x 0 An initial value representing the dynamic characteristic parameter x), an initial iteration step number m=1, and a maximum iteration number M. Select advice distribution q (x) And by x m Generating a new sample x 'of the dynamic characteristic parameter x for the parameter from the proposed distribution q (x)' m . The probability distribution function p (x) of the continuous or discrete dynamic characteristic parameter is input, and the acceptance rate alpha (x) is calculated according to the following formula based on the probability distribution function p (x) m ，x' m )。
Generating pseudo-random numbers u over a uniform distribution of 0-1, comparing u to alpha (x m ，x' m ) If u is the size of>α(x m ，x' m ) X is then m+1 =x m Otherwise, x m+1 =x' m The method comprises the steps of carrying out a first treatment on the surface of the Judging whether the maximum iteration number M is reached, if so<M, m=m+1 and repeating the above steps; otherwise, the cycle is terminated, and the dynamic characteristic parameter value x is output m . Based on the established random human behavior model, dynamic characteristic parameters of the human behavior of the user can be determined. And inputting the determined dynamic characteristic parameters and the determined static characteristic parameters into a later day-ahead optimal scheduling model to perform optimal scheduling calculation.
Step S32: and constructing a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission.
Step S33: and taking the flexible load characteristic model, the power prediction model and the random human behavior model as constraint conditions of the day-ahead optimal scheduling model.
The more detailed processing procedures in steps S32 and S33 refer to the content of the foregoing disclosed embodiments, and are not described herein.
Step S34: and solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain an optimal solution of flexible load optimal scheduling of the residential building.
In this embodiment, the solving the day-ahead optimal scheduling model by using a linear programming method to obtain an optimal solution of flexible load optimal scheduling of the residential building includes: writing the day-ahead optimal scheduling model, the flexible load characteristic model, the random human behavior model and the power prediction model into an integrated development environment through a programming language to generate a solving tool; and calling a preset cvxpy library by using the solving tool to solve the day-ahead optimal scheduling model so as to obtain an optimal solution of flexible load optimal scheduling of the residential building. It can be understood that, in order to facilitate the daily optimization scheduling scheme of the flexible load of the residential building, a tool for daily optimization scheduling of the flexible load of the residential building is developed, specifically, the flexible load characteristic model, the random human behavior model, the prediction model and the daily optimization scheduling model which are built are written into the PyCharm through a Python programming language, and the cvxpy library in the Python is called to solve the daily optimization scheduling model, so that the development of the optimization scheduling tool is completed. By the tool, the daily optimal scheduling scheme of the flexible load of the residential building can be rapidly obtained.
Therefore, the random human behavior model constructed by the Markov chain Monte Carlo method based on the Metropolis Hasting algorithm is used for determining the human behavior of the user, the human behavior characteristics of the user are fully considered, the effectiveness of the obtained flexible load day-ahead optimal scheduling scheme is ensured, and the developed tool for the residential building flexible load day-ahead optimal scheduling is easy to understand and operate, has low engineering application threshold and is convenient to popularize and apply.
Referring to fig. 4, the embodiment of the invention discloses a residential building flexible load day-ahead optimizing and dispatching device, which comprises:
the model construction module 11 is used for constructing a day-ahead optimal scheduling model aiming at minimum daily electricity consumption cost, minimum user electricity climbing rate and minimum carbon dioxide emission;
a constraint condition determining module 12, configured to take a flexible load characteristic model, a random pedestrian behavior model and a power prediction model as constraint conditions of the day-ahead optimization scheduling model;
and the solving module 13 is used for solving the day-ahead optimal scheduling model by adopting a linear programming method so as to obtain an optimal solution of flexible load optimal scheduling of the residential building.
Therefore, the application discloses the construction of a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission; taking a flexible load characteristic model, a random human behavior model and a power prediction model as constraint conditions of the day-ahead optimization scheduling model; and solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain a flexible load day-ahead optimal scheduling scheme of the residential building. Therefore, the condition constraint is carried out on the established mixed integer linear programming day-ahead optimal scheduling model, the flexible load characteristic model, the random pedestrian behavior model and the power prediction model are used as constraint conditions, the day-ahead optimal scheduling model is further solved, the influence of random pedestrian behaviors of users in the flexible load optimal scheduling process of the residential building is comprehensively considered, and the optimal scheduling scheme composed of solved parameters can be executed in actual engineering.
Further, the embodiment of the present application further discloses an electronic device, and fig. 5 is a block diagram of the electronic device 20 according to an exemplary embodiment, where the content of the figure is not to be considered as any limitation on the scope of use of the present application.
Fig. 5 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. Wherein the memory 22 is configured to store a computer program that is loaded and executed by the processor 21 to implement the relevant steps in the residential building flexible load day-ahead optimal scheduling method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in the present embodiment may be specifically an electronic computer.
In this embodiment, the power supply 23 is configured to provide an operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 25 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application requirement, which is not limited herein.
Processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 21 may also comprise a main processor, which is a processor for processing data in an awake state, also called CPU (Central Processing Unit ); a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning.
The memory 22 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the resources stored thereon may include an operating system 221, a computer program 222, and the like, and the storage may be temporary storage or permanent storage.
The operating system 221 is used for managing and controlling various hardware devices on the electronic device 20 and the computer program 222, so as to implement the operation and processing of the processor 21 on the mass data 223 in the memory 22, which may be Windows Server, netware, unix, linux, etc. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the residential building flexible load day-ahead optimal scheduling method performed by the electronic device 20 as disclosed in any of the previous embodiments. The data 223 may include, in addition to data received by the electronic device and transmitted by the external device, data collected by the input/output interface 25 itself, and so on.
Further, the application also discloses a computer readable storage medium for storing a computer program; wherein the computer program when executed by the processor implements the residential building flexible load day-ahead optimal scheduling method disclosed previously. For specific steps of the method, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and no further description is given here.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application. The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The invention provides a residential building flexible load day-ahead optimal scheduling method, device, equipment and medium, which are described in detail, wherein specific examples are applied to illustrate the principle and implementation of the invention, and the description of the above examples is only used for helping to understand the method and core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (7)
1. The daily optimal scheduling method for the flexible load of the residential building is characterized by comprising the following steps of:
constructing a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission;
taking a flexible load characteristic model, a random human behavior model and a power prediction model as constraint conditions of the day-ahead optimization scheduling model;
solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain a day-ahead optimal scheduling scheme of the flexible load of the residential building;
before the flexible load characteristic model, the random pedestrian behavior model and the power prediction model are used as constraint conditions of the day-ahead optimization scheduling model, the method further comprises the following steps:
Determining a human behavior characteristic parameter describing the behavior of a user aiming at a flexible load person and probability distribution of the human behavior characteristic parameter, and establishing a Monte Carlo random human behavior model based on a Markov chain;
the determining of the human behavior characteristic parameters describing the behavior of the user aiming at the flexible load human and the probability distribution of the human behavior characteristic parameters, and the establishment of the Monte Carlo random human behavior model based on the Markov chain comprises the following steps: determining a pedestrian behavior static characteristic parameter, a discrete type pedestrian behavior dynamic characteristic parameter and a continuous type pedestrian behavior dynamic characteristic parameter; determining probability distribution of the discrete human behavior dynamic characteristic parameters in a frequency estimation mode; visualizing the continuous type pedestrian behavior dynamic characteristic parameters, and determining probability distribution of the continuous type pedestrian behavior dynamic characteristic parameters by utilizing a parameter estimation mode; establishing a random human behavior model for determining human behaviors of a user by adopting a Markov chain Monte Carlo method based on Metropolis Hasting algorithm; wherein the dynamic characteristic parameter: for a temperature controlled load, comprising: frequency of use per day, opening time and operation duration; for transferable loads, comprising: frequency of use per day, mode of operation; static characteristic parameters: for a temperature controlled load, comprising: a temperature setting preference; for transferable loads, comprising: a flexible window;
The constraint condition of the day-ahead optimization scheduling model by using the flexible load characteristic model, the random pedestrian behavior model and the power prediction model comprises the following steps:
constructing a flexible load characteristic model comprising a temperature control load characteristic model and a transferable load characteristic model; the temperature control load characteristic model is a characteristic model for changing the power consumption curve of the temperature control load by adjusting the set temperature of the temperature control load; the transferable load characteristic model is a characteristic model for transferring the electric load by adjusting the running time of the transferable load;
predicting a predicted value of the current electric power of the inflexible load based on the historical inflexible load power data and a power prediction model so as to use the predicted value as a constraint condition of the day-ahead optimal scheduling model;
the construction of a day-ahead optimal scheduling model targeting minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission comprises the following steps:
the day-ahead optimal scheduling model comprises three parts: decision variables, objective functions and constraints; wherein the decision variables include: the set temperature of the temperature control load and the starting operation time of the transferable load; the constraint conditions include: the power taken from the power grid at a certain moment is equal to the energy balance constraint of the sum of the power consumption of the flexible load and the inflexible power consumption of the flexible load at the moment, and the optimization space constraint and the operation constraint of the decision variable; and the parameters of the optimization space constraint and the operation constraint of the decision variable are obtained by calculation of a random human behavior model.
2. The residential building flexible load day-ahead optimal scheduling method according to claim 1, wherein the flexible load characteristic model, the random pedestrian behavior model and the power prediction model are used as constraint conditions of the day-ahead optimal scheduling model, and further comprising:
a random human behavior model for determining human behavior of the user is established using a preset machine learning algorithm.
3. The residential building flexible load day-ahead optimal scheduling method according to claim 1, wherein the flexible load characteristic model, the random pedestrian behavior model and the power prediction model are used as constraint conditions of the day-ahead optimal scheduling model, and further comprising:
based on historical inflexible load power data of the inflexible load power, the current inflexible load power is predicted by a heuristic prediction method.
4. The residential building flexible load day-ahead optimal scheduling method according to claim 1, wherein the solving the day-ahead optimal scheduling model by adopting a linear programming method to obtain a residential building flexible load day-ahead optimal scheduling scheme comprises the following steps:
writing the day-ahead optimal scheduling model, the flexible load characteristic model, the random human behavior model and the power prediction model into an integrated development environment through a programming language to generate a solving tool;
And calling a preset cvxpy library by using the solving tool to solve the day-ahead optimal scheduling model so as to obtain an optimal solution of flexible load optimal scheduling of the residential building.
5. A residential building flexible load day-ahead optimal scheduling device, comprising:
the model construction module is used for constructing a day-ahead optimal scheduling model aiming at minimum daily electricity cost, minimum user electricity climbing rate and minimum carbon dioxide emission;
the constraint condition determining module is used for taking the flexible load characteristic model, the random pedestrian behavior model and the power prediction model as constraint conditions of the day-ahead optimal scheduling model;
the solving module is used for solving the day-ahead optimal scheduling model by adopting a linear programming method so as to obtain a day-ahead optimal scheduling scheme of the flexible load of the residential building;
the residential building flexible load day-ahead optimization scheduling device is specifically used for determining a human behavior characteristic parameter describing the behavior of a user aiming at a flexible load person and probability distribution of the human behavior characteristic parameter, and establishing a Monte Carlo random human behavior model based on a Markov chain;
the residential building flexible load day-ahead optimizing and scheduling device is also used for determining the static characteristic parameters of the pedestrians, the dynamic characteristic parameters of the discrete pedestrians and the dynamic characteristic parameters of the continuous pedestrians; determining probability distribution of the discrete human behavior dynamic characteristic parameters in a frequency estimation mode; visualizing the continuous type pedestrian behavior dynamic characteristic parameters, and determining probability distribution of the continuous type pedestrian behavior dynamic characteristic parameters by utilizing a parameter estimation mode; establishing a random human behavior model for determining human behaviors of a user by adopting a Markov chain Monte Carlo method based on Metropolis Hasting algorithm; wherein the dynamic characteristic parameter: for a temperature controlled load, comprising: frequency of use per day, opening time and operation duration; for transferable loads, comprising: frequency of use per day, mode of operation; static characteristic parameters: for a temperature controlled load, comprising: a temperature setting preference; for transferable loads, comprising: a flexible window;
The constraint condition determining module is specifically used for constructing a flexible load characteristic model comprising a temperature control load characteristic model and a transferable load characteristic model; the temperature control load characteristic model is a characteristic model for changing the power consumption curve of the temperature control load by adjusting the set temperature of the temperature control load; the transferable load characteristic model is a characteristic model for transferring the electric load by adjusting the running time of the transferable load; predicting a predicted value of the current electric power of the inflexible load based on the historical inflexible load power data and a power prediction model so as to use the predicted value as a constraint condition of the day-ahead optimal scheduling model;
the model construction module is used for constructing the day-ahead optimal scheduling model and comprises three parts: decision variables, objective functions and constraints; wherein the decision variables include: the set temperature of the temperature control load and the starting operation time of the transferable load; the constraint conditions include: the power taken from the power grid at a certain moment is equal to the energy balance constraint of the sum of the power consumption of the flexible load and the inflexible power consumption of the flexible load at the moment, and the optimization space constraint and the operation constraint of the decision variable; and the parameters of the optimization space constraint and the operation constraint of the decision variable are obtained by calculation of a random human behavior model.
6. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the residential building flexible load day before optimal scheduling method as claimed in any one of claims 1 to 4.
7. A computer-readable storage medium storing a computer program; wherein the computer program when executed by a processor implements the steps of the residential building flexible load day before optimal scheduling method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280030.1A CN115994627B (en) | 2023-03-22 | 2023-03-22 | Residential building flexible load day-ahead optimal scheduling method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280030.1A CN115994627B (en) | 2023-03-22 | 2023-03-22 | Residential building flexible load day-ahead optimal scheduling method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115994627A CN115994627A (en) | 2023-04-21 |
| CN115994627B true CN115994627B (en) | 2023-07-14 |
Family
ID=85993700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310280030.1A Active CN115994627B (en) | 2023-03-22 | 2023-03-22 | Residential building flexible load day-ahead optimal scheduling method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115994627B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892982B (en) * | 2024-03-14 | 2024-06-21 | 国家电投集团云南国际电力投资有限公司 | Power consumption scheduling method, device and equipment for light Chu Zhi flexible building and storage medium |
| CN118674233A (en) * | 2024-08-21 | 2024-09-20 | 深圳大学 | Method, device, equipment and storage medium for optimally adjusting building flexibility energy |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111509727A (en) * | 2019-01-30 | 2020-08-07 | 国网能源研究院有限公司 | User load curve modeling method for distributed power supply based on user behaviors |
| CN113659569A (en) * | 2021-08-09 | 2021-11-16 | 国网北京市电力公司 | Day-ahead optimal scheduling method and system for power system |
| WO2023010759A1 (en) * | 2021-08-04 | 2023-02-09 | 国网江苏省电力有限公司南通供电分公司 | Power distribution and sale competitive situation-based regional power distribution network gridding load interval prediction method |
| CN115775046A (en) * | 2022-12-05 | 2023-03-10 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Virtual power plant optimal scheduling method and system, electronic equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109462231B (en) * | 2018-11-15 | 2020-09-01 | 合肥工业大学 | Load optimization scheduling method, system and storage medium for residential micro-grid |
| CN109474013A (en) * | 2018-12-12 | 2019-03-15 | 天津大学 | The increment power distribution network of the distributed photovoltaic containing Thief zone Optimization Scheduling a few days ago |
| CN111340270B (en) * | 2020-02-10 | 2022-07-12 | 河海大学 | Intelligent household energy optimization method based on information interaction |
| CN114418249B (en) * | 2022-04-01 | 2022-07-08 | 湖南大学 | Operation control method and device for light storage flexible system |
| CN114977330B (en) * | 2022-07-11 | 2022-11-04 | 湖南大学 | Building distributed photovoltaic-storage battery system continuous operation scheduling method and platform |
| CN115241927B (en) * | 2022-09-22 | 2022-11-29 | 湖南大学 | Operation control method, device, equipment and medium for household intelligent energy system |
-
2023
- 2023-03-22 CN CN202310280030.1A patent/CN115994627B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111509727A (en) * | 2019-01-30 | 2020-08-07 | 国网能源研究院有限公司 | User load curve modeling method for distributed power supply based on user behaviors |
| WO2023010759A1 (en) * | 2021-08-04 | 2023-02-09 | 国网江苏省电力有限公司南通供电分公司 | Power distribution and sale competitive situation-based regional power distribution network gridding load interval prediction method |
| CN113659569A (en) * | 2021-08-09 | 2021-11-16 | 国网北京市电力公司 | Day-ahead optimal scheduling method and system for power system |
| CN115775046A (en) * | 2022-12-05 | 2023-03-10 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Virtual power plant optimal scheduling method and system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115994627A (en) | 2023-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115994627B (en) | Residential building flexible load day-ahead optimal scheduling method, device, equipment and medium | |
| Pallonetto et al. | Demand response algorithms for smart-grid ready residential buildings using machine learning models | |
| Lissa et al. | Deep reinforcement learning for home energy management system control | |
| CN110866641B (en) | Two-stage optimization scheduling method and system for multi-energy complementary system considering source storage load coordination | |
| Pinto et al. | Data-driven district energy management with surrogate models and deep reinforcement learning | |
| US10911257B2 (en) | Context-aware smart home energy manager | |
| Jiang et al. | Household energy demand management strategy based on operating power by genetic algorithm | |
| CN114418249B (en) | Operation control method and device for light storage flexible system | |
| Mehdi et al. | Electricity consumption constraints for smart-home automation: An overview of models and applications | |
| Peirelinck et al. | Using reinforcement learning for optimizing heat pump control in a building model in Modelica | |
| CN102142062A (en) | Method and apparatus for controlling operations of devices based on information about power consumption of the devices | |
| Najafi-Ghalelou et al. | Risk-based scheduling of smart apartment building under market price uncertainty using robust optimization approach | |
| Soares et al. | Using reinforcement learning for maximizing residential self-consumption–Results from a field test | |
| Loesch et al. | Demand side management in smart buildings by intelligent scheduling of heat pumps | |
| CN114841409A (en) | Household energy management method and medium combining LSTM and deep reinforcement learning | |
| Jin et al. | User-preference-driven model predictive control of residential building loads and battery storage for demand response | |
| Shann et al. | Adaptive home heating under weather and price uncertainty using GPs and MDPs | |
| Luo et al. | Many-objective day-ahead optimal scheduling of residential flexible loads integrated with stochastic occupant behavior models | |
| Wang et al. | Analysis of predicted mean vote-based model predictive control for residential HVAC systems | |
| Manzoor et al. | Towards simulating the constraint-based nature-inspired smart scheduling in energy intelligent buildings | |
| Chen et al. | Improving power quality efficient in demand response: Aggregated heating, ventilation and air-conditioning systems | |
| Maroufi et al. | A novel energy management model among interdependent sections in the smart grids | |
| Constantinou et al. | An iot data system for solar self-consumption | |
| CN109343461A (en) | A kind of energy-saving control method of building automatic control system | |
| CN116151032B (en) | Residential building dynamic load flexible potential calculation method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |